The database systems course in an undergraduate computer science degree program is gaining increasing importance due to the con- tinuous supply of database-related jobs as well as the rise of Data Science. A key learning goal of learners taking such a course is to understand how sql queries are executed in an rdbms in practice. Existing rdbms typically expose a query execution plan (qep) in visual or textual format, which describes the execution steps for a given query. However, it is often daunting for a learner to compre- hend these qeps containing vendor-specific implementation details. In this demonstration, we present a novel, generic, and portable system called lantern that generates a natural language-based description of the execution strategy chosen by the underlying rdbms to process a query. It provides a declarative framework called pool for subject matter experts (sme) to efficiently create and ma- nipulate natural language descriptions of physical operators of any rdbms. It then exploits pool to generate nl description of a qep by integrating rule-based and deep learning-based techniques to infuse language variability in the descriptions. Such nl generation strategy mitigates the impact of boredom on learners caused by repeated exposure of similar text generated by rule-based systems.
LANTERN: Boredom-conscious Natural Language Description Generation of Query Execution Plans for Database Education
Peng Chen, Hui Li, Sourav Bhowmick, Shafiq Joty, and Weiguo Wang. In Proceedings of 2022 ACM SIGMOD International Conference on Management of Data (Demo) (SIGMOD'22 (Demo)) , pages x - x, 2022.
PDF Abstract BibTex Slides